Add BERTopic model

README.md

@@ -0,0 +1,107 @@
+
+---
+tags:
+- bertopic
+library_name: bertopic
+pipeline_tag: text-classification
+---
+
+# predict_rugby
+
+This is a [BERTopic](https://github.com/MaartenGr/BERTopic) model. 
+BERTopic is a flexible and modular topic modeling framework that allows for the generation of easily interpretable topics from large datasets. 
+
+## Usage 
+
+To use this model, please install BERTopic:
+
+```
+pip install -U bertopic
+```
+
+You can use the model as follows:
+
+```python
+from bertopic import BERTopic
+topic_model = BERTopic.load("rociortizb/predict_rugby")
+
+topic_model.get_topic_info()
+```
+
+## Topic overview
+
+* Number of topics: 40
+* Number of training documents: 27774
+
+<details>
+  <summary>Click here for an overview of all topics.</summary>
+  
+  | Topic ID | Topic Keywords | Topic Frequency | Label | 
+|----------|----------------|-----------------|-------| 
+| 0 | blacks - new - new zealand - zealand - hurricanes | 1556 | 0_blacks_new_new zealand_zealand | 
+| 1 | springboks - south - africa - south africa - erasmus | 1297 | 1_springboks_south_africa_south africa | 
+| 2 | springbok - springboks - year - players - world | 1205 | 2_springbok_springboks_year_players | 
+| 3 | stormers - lions - van - said - team | 1163 | 3_stormers_lions_van_said | 
+| 4 | cheetahs - van - griquas - pumas - province | 1149 | 4_cheetahs_van_griquas_pumas | 
+| 5 | sevens - series - fiji - blitzboks - pool | 994 | 5_sevens_series_fiji_blitzboks | 
+| 6 | brumbies - reds - rebels - rugby - super | 953 | 6_brumbies_reds_rebels_rugby | 
+| 7 | premiership - tom - exeter - wasps - saracens | 928 | 7_premiership_tom_exeter_wasps | 
+| 8 | ireland - sexton - schmidt - irish - leinster | 911 | 8_ireland_sexton_schmidt_irish | 
+| 9 | france - french - racing - year - club | 904 | 9_france_french_racing_year | 
+| 10 | try - leinster - minutes - munster - penalty | 876 | 10_try_leinster_minutes_munster | 
+| 11 | stormers - lions - south - game - team | 870 | 11_stormers_lions_south_game | 
+| 12 | sharks - du - preez - du preez - bosch | 851 | 12_sharks_du_preez_du preez | 
+| 13 | wallabies - australia - folau - rugby - said | 837 | 13_wallabies_australia_folau_rugby | 
+| 14 | england - jones - harlequins - squad - george | 807 | 14_england_jones_harlequins_squad | 
+| 15 | england - jones - world - world cup - wales | 790 | 15_england_jones_world_world cup | 
+| 16 | crusaders - highlanders - hurricanes - blues - chiefs | 769 | 16_crusaders_highlanders_hurricanes_blues | 
+| 17 | italy - france - england - ireland - scotland | 763 | 17_italy_france_england_ireland | 
+| 18 | wallabies - australia - cheika - said - blacks | 736 | 18_wallabies_australia_cheika_said | 
+| 19 | disciplinary - committee - foul play - foul - player | 722 | 19_disciplinary_committee_foul play_foul | 
+| 20 | clermont - stade - montpellier - toulon - toulouse | 688 | 20_clermont_stade_montpellier_toulon | 
+| 21 | blacks - new - zealand - new zealand - foster | 673 | 21_blacks_new_zealand_new zealand | 
+| 22 | wales - davies - ospreys - scarlets - cardiff | 666 | 22_wales_davies_ospreys_scarlets | 
+| 23 | bulls - van - stormers - lions - sharks | 660 | 23_bulls_van_stormers_lions | 
+| 24 | bulls - van - white - rugby - loftus | 615 | 24_bulls_van_white_rugby | 
+| 25 | rugby - super - super rugby - competition - new | 531 | 25_rugby_super_super rugby_competition | 
+| 26 | scotland - glasgow - edinburgh - townsend - russell | 529 | 26_scotland_glasgow_edinburgh_townsend | 
+| 27 | brumbies - waratahs - reds - rebels - force | 521 | 27_brumbies_waratahs_reds_rebels | 
+| 28 | pro14 - leinster - ulster - scarlets - 19 | 490 | 28_pro14_leinster_ulster_scarlets | 
+| 29 | rugby - world - world rugby - nations - cup | 467 | 29_rugby_world_world rugby_nations | 
+| 30 | argentina - santiago - pumas - juan - matias | 447 | 30_argentina_santiago_pumas_juan | 
+| 31 | club - premiership - season - rugby - gloucester | 436 | 31_club_premiership_season_rugby | 
+| 32 | club - premiership - saracens - wasps - salary | 423 | 32_club_premiership_saracens_wasps | 
+| 33 | gatland - lions - wales - tour - barbarians | 361 | 33_gatland_lions_wales_tour | 
+| 34 | africa - south africa - south - zealand - new zealand | 339 | 34_africa_south africa_south_zealand | 
+| 35 | marais - saru - union - rugby - president | 317 | 35_marais_saru_union_rugby | 
+| 36 | kings - southern kings - southern - davids - schalk | 217 | 36_kings_southern kings_southern_davids | 
+| 37 | vs - referees - match official - official - assistant referees | 171 | 37_vs_referees_match official_official | 
+| 38 | sunwolves - japan - super - super rugby - 15 | 116 | 38_sunwolves_japan_super_super rugby | 
+| 39 | burgess - lancaster - england - bath - union | 26 | 39_burgess_lancaster_england_bath |
+  
+</details>
+
+## Training hyperparameters
+
+* calculate_probabilities: False
+* language: None
+* low_memory: False
+* min_topic_size: 10
+* n_gram_range: (1, 1)
+* nr_topics: None
+* seed_topic_list: [['United Rugby Championship', 'Ireland', 'Wales', 'Scotland', 'South Africa', 'Italian', 'Pro14'], ['Pro14', 'Edinburgh', 'Glasgow', 'Scarlets', 'Ospreys', 'Zebre', 'Benetton', 'Connacht', 'Leinster', 'Ulster', 'Munster'], ['European Cup', 'European', 'Heineken', 'competition', 'Toulon', 'Saracens', 'Leinster'], ['Premiership', 'England', 'Exeter', 'Saracens', 'Wasps', 'Leicester', 'Harlequins', 'Sale', 'Bristol', 'Northampton'], ['Sevens', 'Fiji', 'New Zealand', 'South Africa', 'England', 'Australia', 'series', 'HSBC', 'Olympics'], ['Super Rugby', 'New Zealand', 'Australia', 'South Africa', 'Argentina', 'Japan', 'Blues', 'Brumbies', 'Crusaders', 'Sharks', 'Stormers'], ['Six Nations', 'England', 'Wales', 'Ireland', 'Scotland', 'France', 'Italy', 'Championship', 'Grand Slam'], ['Currie Cup', 'South Africa', 'Bulls', 'Lions', 'Sharks', 'Cheetahs', 'Western Province', 'domestic', 'provincial'], ['World Cup', 'international', 'New Zealand', 'Australia', 'South Africa', 'England', 'Wales', 'France'], ['Rugby Championship', 'New Zealand', 'Australia', 'South Africa', 'Argentina', 'All Blacks', 'Wallabies', 'Springboks', 'Pumas'], ['British Irish Lions', 'South Africa', 'New Zealand', 'Australia']]
+* top_n_words: 30
+* verbose: True
+
+## Framework versions
+
+* Numpy: 1.21.0
+* HDBSCAN: 0.8.29
+* UMAP: 0.5.3
+* Pandas: 2.0.2
+* Scikit-Learn: 1.2.2
+* Sentence-transformers: 2.2.2
+* Transformers: 4.29.2
+* Numba: 0.57.0
+* Plotly: 5.14.1
+* Python: 3.9.6

config.json

@@ -0,0 +1,131 @@
+{
+  "calculate_probabilities": false,
+  "language": null,
+  "low_memory": false,
+  "min_topic_size": 10,
+  "n_gram_range": [
+    1,
+    1
+  ],
+  "nr_topics": null,
+  "seed_topic_list": [
+    [
+      "United Rugby Championship",
+      "Ireland",
+      "Wales",
+      "Scotland",
+      "South Africa",
+      "Italian",
+      "Pro14"
+    ],
+    [
+      "Pro14",
+      "Edinburgh",
+      "Glasgow",
+      "Scarlets",
+      "Ospreys",
+      "Zebre",
+      "Benetton",
+      "Connacht",
+      "Leinster",
+      "Ulster",
+      "Munster"
+    ],
+    [
+      "European Cup",
+      "European",
+      "Heineken",
+      "competition",
+      "Toulon",
+      "Saracens",
+      "Leinster"
+    ],
+    [
+      "Premiership",
+      "England",
+      "Exeter",
+      "Saracens",
+      "Wasps",
+      "Leicester",
+      "Harlequins",
+      "Sale",
+      "Bristol",
+      "Northampton"
+    ],
+    [
+      "Sevens",
+      "Fiji",
+      "New Zealand",
+      "South Africa",
+      "England",
+      "Australia",
+      "series",
+      "HSBC",
+      "Olympics"
+    ],
+    [
+      "Super Rugby",
+      "New Zealand",
+      "Australia",
+      "South Africa",
+      "Argentina",
+      "Japan",
+      "Blues",
+      "Brumbies",
+      "Crusaders",
+      "Sharks",
+      "Stormers"
+    ],
+    [
+      "Six Nations",
+      "England",
+      "Wales",
+      "Ireland",
+      "Scotland",
+      "France",
+      "Italy",
+      "Championship",
+      "Grand Slam"
+    ],
+    [
+      "Currie Cup",
+      "South Africa",
+      "Bulls",
+      "Lions",
+      "Sharks",
+      "Cheetahs",
+      "Western Province",
+      "domestic",
+      "provincial"
+    ],
+    [
+      "World Cup",
+      "international",
+      "New Zealand",
+      "Australia",
+      "South Africa",
+      "England",
+      "Wales",
+      "France"
+    ],
+    [
+      "Rugby Championship",
+      "New Zealand",
+      "Australia",
+      "South Africa",
+      "Argentina",
+      "All Blacks",
+      "Wallabies",
+      "Springboks",
+      "Pumas"
+    ],
+    [
+      "British Irish Lions",
+      "South Africa",
+      "New Zealand",
+      "Australia"
+    ]
+  ],
+  "top_n_words": 30,
+  "verbose": true
+}

ctfidf.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9346a4b72bdc68c338b1264286e3e760b9e6bab518dc5b8e192cbd87cc8136bf
+size 6540360

topic_embeddings.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e644122483ea54b6e85b3fab02d4a97ca4e4b98558d73bc8fe88279dde8c91a1
+size 61528